AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

DiffGraph: An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image Generation

Zhuoling Li, Hossein Rahmani, Jiarui Zhang, Yu Xue, Majid Mirmehdi, Jason Kuen, Jiuxiang Gu, Jun Liu

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add node registration (text node features) (ablation)DiffGraph · DABench (SD15)ImageReward: 31.04 -> 73.11Improved
use fixed text features instead of learnable registration embeddings (ablation)DiffGraph · DABench (SD15)ImageReward: 33.36 -> 73.11Improved
add node calibration (quality-score edge features) (ablation)DiffGraph · DABench (SD15)ImageReward: 11.92 -> 73.11Improved
use measured edge features instead of learnable ones (ablation)DiffGraph · DABench (SD15)ImageReward: 19.63 -> 73.11Improved
add Expert Selection Agent (ablation)DiffGraph · DABench (SD15)ImageReward: 16.12 -> 73.11Improved
select experts with ESA instead of random activation (ablation)DiffGraph · DABench (SD15)ImageReward: 15.36 -> 73.11Improved
use VGAE merging planner instead of equal weights (ablation)DiffGraph · DABench (SD15)ImageReward: 13.29 -> 73.11Improved
use VGAE instead of LLM-produced coefficients (ablation)DiffGraph · DABench (SD15)ImageReward: 18.00 -> 73.11Improved
use text/score node features instead of expert parameters (ablation)DiffGraph · DABench (SD15)ImageReward: 26.62 -> 73.11Improved
add new experts via registration+calibration without retraining (ablation)DiffGraph · DABench (SD15)ImageReward: 43.96 -> 69.64Improved
add new experts post hoc (ablation)ESA*+K-LoRA · DABench (SD15)ImageReward: 13.91 -> 19.33Improved
graph-based merging vs best baseline DiffAgentDiffGraph · DABench (FLUX)ImageReward: 100.20 -> 136.62Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy